Change detection of open-pit mines based on FM-UNet++ and GF-2 satellite images

Authors

DU Shouhang, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow
LI Wei, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
XING Jianghe, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
ZHANG Chengye, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
SHE Changchao, Guoneng Beidian Shengli Energy Co., Ltd., Xilinhot 026015, China
WANG Shaoyu, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
LI Jun, College of Geosciences and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow

Abstract

Automatic extraction of land use change information in open-pit mines using the remote sensing and deep learning technology is of great significance for the mining monitoring and ecological environmental protection. A novel deep learning model FM-UNet++ was constructed for the change of land use types in complex and heterogeneous mining scenarios, and the automatic change detection of open-pit mines was achieved using the Gaofen-2 (GF-2) satellite images. Firstly, the change detection dataset of open-pit mine was produced through data surveys and visual interpretation, which was augmented by data enhancement. Secondly, the FM-UNet++ for open-pit mine change detection was constructed by introducing the Feature-enhanced Coordinate Attention (FECA) mechanism and the Mish activation function into the UNet++. Finally, FM-UNet++ and 7 comparative models were trained for the change detection experiment of open-pit mine and the detection results of different deep learning models were compared. The results show that: (1) The FECA mechanism and the Mish activation function both improve the performance of the UNet++ for open-pit mine change detection. (2) The precision, recall, F1-Score and IoU of FM-UNet++ model are 95.6%, 89.2%, 92.3% and 85.7% respectively for the change detection of open-pit mine, which is significantly improved compared with the deep learning models such as FCN, PSPNet, Deeplab v3+, LANet, UNet, UNet++ and DA-UNet++. Besides, the change detection speed of the FM-UNet++ model remains in the same order of magnitude as the 7 comparative models mentioned above, with a stable training process, validating the feasibility of applying the FM-UNet++ model to the change detection in open-pit mines.

Keywords

open-pit mine, GF-2 satellite, UNet++, change detection, convolutional neural network

DOI

10.12363/issn.1001-1986.22.12.0972

Recommended Citation

DU Shouhang, LI Wei, XING Jianghe, et al. (2023) "Change detection of open-pit mines based on FM-UNet++ and GF-2 satellite images," Coal Geology & Exploration: Vol. 51: Iss. 7, Article 15.
DOI: 10.12363/issn.1001-1986.22.12.0972
Available at: https://cge.researchcommons.org/journal/vol51/iss7/15

Reference

[1] 李军,彭苏萍,张成业,等. 矿区生态环境定量遥感监测评价技术框架与应用[J]. 矿业科学学报,2022,7(1):9−25.

LI Jun,PENG Suping,ZHANG Chengye,et al. Quantitative remote sensing–based monitoring and evaluation of the ecological environment in mining areas:Technology framework and application[J]. Journal of Mining Science and Technology,2022,7(1):9−25.

[2] 张成业,李军,雷少刚,等. 矿区生态环境定量遥感监测研究进展与展望[J]. 金属矿山,2022(3):1−27.

ZHANG Chengye,LI Jun,LEI Shaogang,et al. Progress and prospect of the quantitative remote sensing for monitoring the eco–environment in mining area[J]. Metal Mine,2022(3):1−27.

[3] 向阳,赵银娣,董霁红. 基于改进UNet孪生网络的遥感影像矿区变化检测[J]. 煤炭学报,2019,44(12):3773−3780.

XIANG Yang,ZHAO Yindi,DONG Jihong. Remote sensing image mining area change detection based on improved UNet siamese network[J]. Journal of China Coal Society,2019,44(12):3773−3780.

[4] 李军,张艺藂,张彩月,等. 基于LandTrendr和CCDC算法的神东煤炭基地植被损毁识别对比分析[J]. 金属矿山,2023,559(1):55−64.

LI Jun,ZHANG Yicong,ZHANG Caiyue,et al. Applicability analysis of land trendr and CCDC algorithms for vegetation damage identification in Shendong coal base[J]. Metal Mine,2023,559(1):55−64.

[5] 李军,彭传盈,张成业,等. 基于大样本的露天开采植被扰动范围一般性统计规律−以神东煤炭基地为例[J]. 煤炭学报,2023,48(2):975−985.

LI Jun,PENG Chuanying,ZHANG Chengye,et al. General statistical rules of vegetation disturbance range by open–pit mining based on a large sample:A case study of Shendong coal base[J]. Journal of China Coal Society,2023,48(2):975−985.

[6] 陈宇,杜培军,唐伟成,等. 基于BJ–1小卫星遥感数据的矿区土地覆盖变化检测[J]. 国土资源遥感,2011(3):146−150.

CHEN Yu,DU Peijun,TANG Weicheng,et al. Land cover change detection in coal mining area using BJ–1 small satellite remote sensing data[J]. Remote Sensing for Land & Resources,2011(3):146−150.

[7] SHI Wenzhong,ZHANG Min,ZHANG Rui,et al. Change detection based on artificial intelligence:State–of–the–art and challenges[J]. Remote Sensing,2020,12(10):1688.

[8] 袁洲,郭海涛,卢俊,等. 融合UNet++网络和注意力机制的高分辨率遥感影像变化检测算法[J]. 测绘科学技术学报,2021,38(2):155−159.

YUAN Zhou,GUO Haitao,LU Jun,et al. High–resolution remote sensing image change detection technology based on UNet++ and attention mechanism[J]. Journal of Geomatics Science and Technology,2021,38(2):155−159.

[9] 杜青松,李国玉,彭万林,等. 基于遥感技术的高寒矿区土地利用变化研究[J]. 环境科学与技术,2020,43(12):185−194.

DU Qingsong,LI Guoyu,PENG Wanlin,et al. Land use changes in high cold–altitude mining area based on remote sensing technology[J]. Environmental Science & Technology,2020,43(12):185−194.

[10] 尚慧,倪万魁. 石嘴山矿区地表环境动态变化遥感监测[J]. 国土资源遥感,2013,25(2):113−120.

SHANG Hui,NI Wankui. Remote sensing monitoring of dynamic changes of surface environment in Shizuishan mining area[J]. Remote Sensing for Land & Resources,2013,25(2):113−120.

[11] 魏矿灵,王启春,郭广礼,等. 利用遥感数据监测矿区开采沉陷积水变化[J]. 煤矿安全,2014,45(1):13−16.

WEI Kuangling,WANG Qichun,GUO Guangli,et al. Using remote sensing data to monitor the change of mining subsidence water accumulation[J]. Safety in Coal Mines,2014,45(1):13−16.

[12] 杜培军,柳思聪,郑辉. 基于支持向量机的矿区土地覆盖变化检测[J]. 中国矿业大学学报,2012,41(2):262−267.

DU Peijun,LIU Sicong,ZHENG Hui. Land cover change detection over mining areas based on support vector machine[J]. Journal of China University of Mining and Technology,2012,41(2):262−267.

[13] 程久龙,王慧杰,徐忠忠,等. 基于全卷积神经网络的钻孔瞬变电磁法岩层富水性预测研究[J]. 煤田地质与勘探,2023,51(1):289−297.

CHENG Jiulong,WANG Huijie,XU Zhongzhong,et al. Research on aquifer water abundance evaluation by borehole transient electromagnetic method based on FCNN[J]. Coal Geology & Exploration,2023,51(1):289−297.

[14] 董丽丽,费城,张翔,等. 基于LSTM神经网络的煤矿突水预测[J]. 煤田地质与勘探,2019,47(2):137−143.

DONG Lili,FEI Cheng,ZHANG Xiang,et al. Coal mine water inrush prediction based on LSTM neural network[J]. Coal Geology & Exploration,2019,47(2):137−143.

[15] LONG J，SHELHAMER E，DARRELL T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston，2015：3431–3440.

[16] ZHAO Hengshuang，SHI Jianping，QI Xiaojuan，et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu，2017：2881–2890.

[17] CHEN L C，ZHU Yukun，PAPANDREOU G，et al. Encoder–decoder with atrous separable convolution for semantic image segmentation[C]//2018 European Conference on Computer Vision (ECCV). Munich, Germany，2018：833–851.

[18] RONNEBERGER O，FISCHER P，BROX T. U–Net：Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer−Assisted Intervention. Cham：Springer，2015：234–241.

[19] ZHOU Zongwei,RAHMAN S M M,NIMA T,et al. UNet++:Redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Transactions on Medical Imaging,2019,39(6):1856−1867.

[20] HUANG Gao，LIU Zhuang，MAATEN L V D，et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu，2017：4700–4708.

[21] MISRA D. Mish:A self regularized non–monotonic neural activation function[J]. CoRR,2019,4(2):10.48550.

[22] HU Jie，SHEN Li，SUN Gang. Squeeze−and−excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City，2018：7132–7141.

[23] WOO S，PARK J，LEE J Y，et al. CBAM：Convolutional block attention module[C]//2018 European Conference on Computer Vision (ECCV). Munich, Germany，2018：3–19.

[24] PARK J，WOO S，LEE J Y，et al. BAM：Bottleneck attention module：10. 48550/arXiv. 1807. 06514[P]. 2018-07-17.

[25] HOU Qibin，ZHOU Daquan，FENG Jiashi. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville，2021：13713–13722.

[26] 张成业,李飞跃,李军,等. 基于DeepLabv3+与GF–2高分辨率影像的露天煤矿区土地利用分类[J]. 煤田地质与勘探,2022,50(6):94−103.

ZHANG Chengye,LI Feiyue,LI Jun,et al. Recognition of land use on open−pit coal mining area based on DeepLabv3+ and GF−2 high−resolution images[J]. Coal Geology & Exploration,2022,50(6):94−103.

[27] LIU Ruochen,JIANG Dawei,ZHANG Langlang,et al. Deep depthwise separable convolutional network for change detection in optical aerial images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:1109−1118.

[28] DING Lei,TANG Hao,BRUZZONE L. LANet:Local attention embedding to improve the semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing,2020,59(1):426−435.

[29] DU Shouhang,LI Wei,LI Jun,et al. Open–pit mine change detection from high resolution remote sensing images using DA–UNet++ and object–based approach[J]. International Journal of Mining,Reclamation and Environment,2022,36(7):512−535.